Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Livus-AI/Skills-MCP --skill a3-thinkinggit clone --depth 1 https://github.com/Livus-AI/Skills-MCPWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/livus-ai/skills-mcp/a3-thinking)<a href="https://agentmods.dev/skills/livus-ai/skills-mcp/a3-thinking"><img src="https://agentmods.dev/badge/skills/livus-ai/skills-mcp/a3-thinking/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/livus-ai/skills-mcp/a3-thinking"><img src="https://agentmods.dev/badge/skills/livus-ai/skills-mcp/a3-thinking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00097 | $0.01032 |
| Opus 5 | $0.00048 | $0.00516 |
| Sonnet 5 | $0.00019 | $0.00206 |
| Haiku 4.5 | $0.00010 | $0.00103 |
Grade A, and why
a3-thinking scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A3 Thinking
Produce an A3: a single-page, story-format document that walks a problem (or proposal, or status) through the PDCA cycle. The artifact is markdown; the value is the thinking — disciplined, fact-based reasoning that resists jumping to solutions.
Core principle: the A3 is the artifact, A3 thinking is the point. Your job is to coach the content into shape first, then save it. A polished template over shallow analysis is a failed A3.
The three variants
| Variant | Use when | Sections |
|---|---|---|
problem-solving |
A real, important problem whose root cause isn't yet understood | Background · Current Condition · Goal · Root-Cause Analysis · Countermeasures · Implementation Plan · Follow-Up |
proposal |
Pitching a new initiative or investment (forward-looking business case) | Background · Current Situation · Goal · Analysis · Proposal · Implementation Plan · Expected Results & Follow-Up |
status |
Reporting progress on an ongoing effort | Background · Current State · Results · Remaining Issues / Next Actions |
If unsure which variant fits, ask. Don't default to problem-solving for work
that is actually a proposal or a status update.
Full section-by-section guidance, root-cause techniques, and when-NOT-to-use are
in references/a3-guide.md. Filled examples per variant are in
references/worked-examples.md. Load them with get_skill_resource when you need
depth.
Workflow (coach first, then save)
- Pick the variant and confirm it fits.
- Work the sections in order, with the user. This is the coaching step — the
bulk of the value. Hold these lines:
- Frame the title as a problem/theme, not a solution ("Shipping errors rising", not "Add barcode scanner").
- Current state before future state. Get facts and a measured gap before any countermeasure. Ask for real data; flag assumptions as assumptions.
- Set a measurable, time-bound target (Goal section).
- For
problem-solving: do root-cause analysis before countermeasures (5-Why / fishbone). Each countermeasure must trace to a root cause. - Keep it tight — an A3 is one page. Cut anything non-essential.
- Save once the content is agreed:
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 87 lines · 97 tokens per session scan A 76e3e92f6a51
a3-thinking is a skill published in the GitHub repository Livus-AI/Skills-MCP (2 stars, last pushed 3mo ago), licensed MIT. It adds 97 tokens to every session and 1,032 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…